xc-llm-ascend/benchmarks/tests/throughput-tests.json

[
  {
    "test_name": "throughput_llama8B_tp1",
    "parameters": {
      "model": "LLM-Research/Meta-Llama-3.1-8B-Instruct",
      "tensor_parallel_size": 1,
      "load_format": "dummy",
      "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200,
      "backend": "vllm"
    }
  },
  {
    "test_name": "throughput_qwen2_5_7B_tp1",
    "parameters": {
      "model": "Qwen/Qwen2.5-7B-Instruct",
      "tensor_parallel_size": 1,
      "load_format": "dummy",
      "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
      "num_prompts": 200,
      "backend": "vllm"
    }
  }
]